本文選題：農(nóng)作物病蟲害檢測 + 卷積神經(jīng)網(wǎng)絡(luò)��； 參考：《哈爾濱工業(yè)大學(xué)》2017年碩士論文

【摘要】：農(nóng)業(yè)生產(chǎn)是我國經(jīng)濟(jì)發(fā)展至關(guān)重要的部分,其產(chǎn)量不僅會影響到國家的經(jīng)濟(jì)發(fā)展,同時也會影響到人們?nèi)粘Ｉ畹馁|(zhì)量。然而,由于傳統(tǒng)的農(nóng)作物病蟲害檢測過多依賴于專家的經(jīng)驗,效率低且不具有智能性是影響其病蟲害檢測性能的重要限制。隨著計算機(jī)視覺以及神經(jīng)網(wǎng)絡(luò)算法的不斷發(fā)展,隨著智能手機(jī)的不斷普及,農(nóng)作物病蟲害的智能檢測越來越多地引起了人們的關(guān)注,并得到了快速的發(fā)展。本文提出了一種基于卷積神經(jīng)網(wǎng)絡(luò)的可見光圖像農(nóng)作物病蟲害的檢測方法,對于農(nóng)作物病蟲害的分類識別有很好的效果。本文提出的基于卷積神經(jīng)網(wǎng)絡(luò)的可見光圖像農(nóng)作物病蟲害的檢測方法,主要結(jié)合了:卷積神經(jīng)網(wǎng)絡(luò)、遷移學(xué)習(xí)思想、支持向量機(jī)分類以及數(shù)據(jù)擴(kuò)充四個方面的技術(shù)。本文也針對這四方面技術(shù)進(jìn)行了詳細(xì)的闡述。在介紹該方法之前,本文對實驗部分要用到的農(nóng)作物病蟲害數(shù)據(jù)集做了詳細(xì)的介紹,同時介紹了一種傳統(tǒng)方法用在該數(shù)據(jù)集上的分類結(jié)果,可以看出傳統(tǒng)方法對于數(shù)據(jù)的分類并不理想。在此之后,本文開始針對檢測方法進(jìn)行介紹。文章首先介紹了僅基于卷積神經(jīng)網(wǎng)絡(luò)的檢測方法。該部分主要針對卷積神經(jīng)網(wǎng)絡(luò)的結(jié)構(gòu)設(shè)計、卷積神經(jīng)網(wǎng)絡(luò)的訓(xùn)練細(xì)節(jié)等做了詳細(xì)的闡述,并列舉了僅基于卷積神經(jīng)網(wǎng)絡(luò)的檢測方法對于農(nóng)作物病蟲害數(shù)據(jù)集的分類情況,并分析了其產(chǎn)生過擬合問題的原因。隨后介紹了基于遷移學(xué)習(xí)思想對于檢測方法的改進(jìn)�？梢钥闯�,遷移學(xué)習(xí)思想能夠較大程度地緩解過擬合問題,使分類檢測精度有了很大的提升。在此之后,我們用支持向量機(jī)取代原先的softmax分類層進(jìn)行分類,可以看出這樣做可以使準(zhǔn)確率小幅度提升,對于緩解過擬合問題有一定的作用。最后,介紹了數(shù)據(jù)擴(kuò)充對于緩解過擬合問題、提升病蟲害檢測精度的重要意義,并給出相關(guān)的驗結(jié)論。此外,本文還將提出的該農(nóng)作物病蟲害的檢測方法應(yīng)用于自己建立的數(shù)據(jù)集,也可以實現(xiàn)較高的分類精度,說明該方法具有較好的穩(wěn)健性。本文提出的基于卷積神經(jīng)網(wǎng)絡(luò)的可見光圖像農(nóng)作物病蟲害的檢測方法,相比于傳統(tǒng)方法而言,對于病蟲害檢測具有良好的檢測性能,其智能性和高準(zhǔn)確性對于實際問題的解決有很好的效果。
[Abstract]:Agricultural production is a vital part of the economic development of our country. Its output will not only affect the economic development of the country, but also affect the quality of people's daily life. However, because the traditional crop pest detection depends too much on the experience of experts, low efficiency and lack of intelligence is an important limitation affecting the performance of crop pest detection. With the development of computer vision and neural network algorithms, and with the popularity of smart phones, the intelligent detection of crop diseases and insect pests has attracted more and more attention, and has been rapidly developed. In this paper, a method of crop pest detection based on convolution neural network is proposed, which has a good effect on the classification and recognition of crop pests and diseases. In this paper, the method of detecting crop pests and diseases in visible light image based on convolution neural network is proposed, which mainly combines four techniques: convolution neural network, migration learning idea, support vector machine classification and data expansion. This article also has carried on the detailed elaboration to these four aspects technology. Before introducing this method, this paper introduces the data set of crop diseases and insect pests used in the experiment in detail, and introduces the classification results of a traditional method used in the data set. It can be seen that the traditional method for data classification is not ideal. After this, this article begins to carry on the introduction to the detection method. Firstly, the detection method based on convolution neural network is introduced. In this part, the structure design of convolutional neural network and the training details of convolutional neural network are described in detail, and the classification of crop diseases and insect pests data set based only on convolution neural network detection method is listed. The reason of over-fitting problem is analyzed. Then the improvement of detection method based on transfer learning is introduced. It can be seen that the idea of transfer learning can alleviate the problem of over-fitting to a great extent and improve the accuracy of classification and detection greatly. After that, we use support vector machine instead of the original softmax classification layer to classify. It can be seen that this method can improve the accuracy slightly, and has a certain role in alleviating the problem of over-fitting. Finally, the importance of data expansion in alleviating the problem of over-fitting and improving the accuracy of disease and pest detection is introduced, and the relevant test results are given. In addition, the method proposed in this paper is applied to the data set established by ourselves, and it can also achieve higher classification accuracy, which shows that the method has good robustness. In this paper, a new method based on convolution neural network is proposed to detect crop diseases and insect pests in visible light images. Compared with traditional methods, it has a good performance in detecting pests and diseases. Its intelligence and high accuracy have a good effect on the solution of practical problems.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：S432;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王長斌;;基于云計算的農(nóng)作物病蟲害多源遙感數(shù)據(jù)挖掘[J];電子技術(shù);2016年03期

2 賈世杰;楊東坡;劉金環(huán);;基于卷積神經(jīng)網(wǎng)絡(luò)的商品圖像精細(xì)分類[J];山東科技大學(xué)學(xué)報(自然科學(xué)版);2014年06期

3 汪京京;張武;劉連忠;黃帥;;農(nóng)作物病蟲害圖像識別技術(shù)的研究綜述[J];計算機(jī)工程與科學(xué);2014年07期

4 霍治國;李茂松;王麗;溫泉沛;肖晶晶;黃大鵬;王春艷;;氣候變暖對中國農(nóng)作物病蟲害的影響[J];中國農(nóng)業(yè)科學(xué);2012年10期

5 鄒修國;;基于計算機(jī)視覺的農(nóng)作物病蟲害識別研究現(xiàn)狀[J];計算機(jī)系統(tǒng)應(yīng)用;2011年06期

6 高琪娟;季小闖;樂毅;張友華;韋東華;;基于WEBGIS的農(nóng)業(yè)病蟲害監(jiān)測系統(tǒng)[J];計算機(jī)技術(shù)與發(fā)展;2010年04期

7 張谷豐;朱葉芹;翟保平;;基于WebGIS的農(nóng)作物病蟲害預(yù)警系統(tǒng)[J];農(nóng)業(yè)工程學(xué)報;2007年12期

8 梁子安;劉飛;趙秋紅;杜瑞卿;;數(shù)學(xué)形態(tài)學(xué)在昆蟲總科階元分類學(xué)上的應(yīng)用研究[J];動物分類學(xué)報;2007年01期

9 王劍;周國民;;基于神經(jīng)網(wǎng)絡(luò)的水稻三化螟識別系統(tǒng)的研究[J];農(nóng)業(yè)網(wǎng)絡(luò)信息;2006年02期

10 于新文;沈佐銳;;數(shù)學(xué)形態(tài)學(xué)在田間蚜蟲圖象處理中的初步應(yīng)用[J];中國農(nóng)業(yè)大學(xué)學(xué)報;1998年S3期

相關(guān)博士學(xué)位論文 前1條

1 王克如;基于圖像識別的作物病蟲草害診斷研究[D];中國農(nóng)業(yè)科學(xué)院;2005年

相關(guān)碩士學(xué)位論文 前3條

1 謝寶劍;基于卷積神經(jīng)網(wǎng)絡(luò)的圖像分類方法研究[D];合肥工業(yè)大學(xué);2015年

2 劉雙;基于數(shù)字圖像的農(nóng)業(yè)害蟲精準(zhǔn)檢測算法的研究[D];四川農(nóng)業(yè)大學(xué);2014年

3 唐勝;基于神經(jīng)網(wǎng)絡(luò)的農(nóng)作物病害診斷專家系統(tǒng)的設(shè)計[D];湘潭大學(xué);2001年

，

本文編號：1991893